Graduate Spotlight: Huan Li's Journey Through Yale's CBB PhD Program

Huan Li, PhD ’25, recently completed her doctoral studies in Yale’s Computational Biology and Biomedical Informatics program. Her research focuses on using machine learning to improve electronic health record systems and clinical workflows, with the goal of enhancing provider productivity and patient care. In this interview, she reflects on her interdisciplinary journey, the challenges she embraced, and what lies ahead.

Q: Congratulations on your graduation! Can you briefly introduce your research and its key focus?

A: Thank you! My research focuses on developing computational methods to extract insights from electronic health record (EHR) data. I aim to improve provider productivity and patient outcomes by applying machine learning to real-world clinical workflows. A significant part of my work examines how physicians interact with EHR systems and how to optimize these interactions for efficiency and accuracy.

Q: What inspired you to pursue this area of study in biomedical informatics/computational biology?

A: I was drawn to biomedical informatics because it sits at the intersection of data science, clinical care, and real-world problem-solving. Coming from a computational background, I saw a pressing need to make complex health care systems more intelligent and human-centered. The potential to directly impact patient care and provider well-being motivated me to pursue this path.

Q: For readers less familiar with your work, how would you describe the real-world impact or applications of your research?

A: My work has practical applications in reducing physician burnout by identifying inefficiencies in EHR use, improving diagnostic decision-making, and guiding hospital operational strategies using interpretable AI models. Ultimately, these tools can help hospitals deliver better care while supporting clinicians in their daily work.

Q: What are you most proud of in your dissertation or recent projects?

A: I'm most proud of how my dissertation bridged technical methods with real-world challenges. I worked on a project addressing missing data in EHR audit logs—a technical challenge with major implications for downstream analytics. Both projects required creativity, collaboration, and a deep understanding of clinical context. One highlight was a collaborated project supported by the Yale New Haven Health Innovation Award, where we used AI to investigate UTI diagnostic error and decision noise in emergency medicine.

Q: Your work intersects computational biology and complex biological systems. What breakthroughs or findings from your research excite you the most?

A: What excites me most is how even modest algorithmic improvements can translate into large-scale operational or clinical gains. One exciting aspect is that AI applications are actually applicable to the day-to-day operations of health care systems. Another is seeing interpretable machine learning being used not just to predict outcomes, but to inform system-wide decisions in health care.

Q: How has your experience in the CBB program and within Yale BIDS shaped your approach to research?

A: The CBB program encouraged me to think deeply across disciplines. It gave me the technical skills to develop algorithms and the biomedical grounding to understand where they fit. My time with Yale BIDS further pushed me to consider the social and ethical implications of my work, and to seek out feedback from diverse perspectives.

Q: Were there any mentors, lab environments, or courses that had a particularly strong impact on your journey?

A: Absolutely—my advisor, Edward Melnick, MD, MHS, was instrumental in guiding me through the translational aspects of my work. His ability to bridge research with clinical relevance was something I learned a great deal from. Andrew Loza, MD, PhD, was an incredibly inspiring computational mentor and helped me overcome technical obstacles.

Additionally, courses like Applied Machine Learning in Healthcare helped me build a strong foundation in real-world applications.

Q: How did the interdisciplinary nature of the CBB program support your work across fields like computer science, biology, and medicine?

A: The program's flexibility let me integrate courses and research from computer science, statistics, and health policy. This interdisciplinary training was key to building tools that not only worked technically, but also made sense in a health care environment. Collaborating across departments—whether with clinicians or computer scientists—was a hallmark of my experience.

Q: What was the most challenging part of your PhD journey—and what helped you get through it?

A: The most challenging part of my PhD journey was finding the real research question and realizing that completing a PhD is not just about mastering a specific subject, but about developing a way of thinking grounded in good science. I believe that many—if not all—PhD students have moments when they question why they’re pursuing the degree and what kind of contribution they want to make to their field, their institution, and the broader public. It’s common to lose sleep over these questions.

What helped me get through it was taking the time to truly sit down and read—whether it was scientific papers or even the history of how science has evolved. Talking to people who could help me think more clearly was also incredibly helpful. Ultimately, reflecting on the kind of impact I want to make was what kept me grounded.

Q: What is a lesson or mindset you’re taking with you from your time at Yale?

A: I’ve learned the value of iterative thinking and adaptability. Research is rarely linear, and being able to pause, reassess, and pivot when needed has made me a more resilient scientist. I’ve also come to appreciate the importance of communication—being able to explain your work clearly to a wide audience is essential.

Q: What’s next for you—academia, industry, entrepreneurship?

A: I will be starting a postdoctoral position and am still considering a transition to industry—particularly roles in health care consulting or health data science, where I can apply my skills to system-level challenges. I’m especially interested in work that translates research into operational improvements in health care.

Q: Are there any big questions or problems you're hoping to tackle in the next phase of your career?

A: Yes—one big question I’m interested in is how to optimize clinical workflows at scale using data-driven insights. I also want to contribute to more responsible and equitable AI adoption in health care, ensuring that the models we deploy are transparent, fair, and sustainable.

Q: What advice would you give to incoming CBB PhD students or those just beginning their journey in biomedical informatics and data science?

A: Be curious and open to ambiguity. Some of the most impactful questions won’t have a clear technical answer right away—and that’s okay. Build relationships across disciplines, and don’t underestimate the power of communication. Lastly, take the time to understand the human context of the data you’re working with—it will make your work more meaningful and impactful.

Q: Outside of research, how did you unwind or find community during your PhD years?

A: I found community through the Yale Graduate Consulting Club, where I served as president. It was energizing to work with students from across disciplines on case competitions and workshops. I also kept rabbits during my PhD, which brought a calming presence to my life and reminded me to slow down.

Q: Any fun memory, hobby, or unexpected experience during your time at Yale you’d like to share?

A: During my time at Yale, I had many pets—particularly small animals. I spent half of my PhD during the COVID pandemic, and having living creatures around me was incredibly important. The emotional support from my furry friends was essential to my entire journey.